Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7607
    Prev
    Next
    INDEX
    Explanations

    elements related to measurement and evaluation in data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.58
    '
    -0.57
    <bos>
    -0.45
     Gar
    -0.44
     is
    -0.42
    ’
    -0.42
     Per
    -0.42
    6
    -0.41
     sa
    -0.40
     ra
    -0.39
    POSITIVE LOGITS
     ―――――
    0.96
    Datuak
    0.94
     Majefty
    0.94
    ſelves
    0.87
     Houſe
    0.87
     Efq
    0.85
     '\\;'
    0.84
    Personendaten
    0.83
     nonatomic
    0.82
     $_"
    0.81
    Activations Density 0.789%

    No Known Activations